Improving tag transfer for image annotation using visual and semantic information

Simple item page
dc.contributor.authorRodriguez-Vaamonde, Sergio
dc.contributor.authorTorresani, Lorenzo
dc.contributor.authorEspinosa, Koldo
dc.contributor.authorGarrote, Estibaliz
dc.contributor.institutionTecnalia Research & Innovation
dc.date.accessioned2024-07-24T11:46:10Z
dc.date.available2024-07-24T11:46:10Z
dc.date.issued2014
dc.description.abstractThis paper addresses the problem of image annotation using a combination of visual and semantic information. Our model involves two stages: a Nearest Neighbor computation and a tag transfer stage that collects the final annotations. For the latter stage, several algorithms have been implemented in the past using labels' information or including implicitly some visual features. In this paper we propose a novel algorithm for tag transfer that takes advantage explicitly of semantic and visual information. We also present a structured training procedure based on a concept we have called Image Networking: all the images in a training database are 'connected' visually and semantically, so it is possible to exploit these connections to learn the tag transfer parameters at annotation time. This learning is local for the test image and it exploits the information obtained in the Nearest Neighbor computation stage. We demonstrate that our approach achieves state-of-The-art performance on the ImageCLEF2011 dataset.en
dc.description.statusPeer reviewed
dc.identifier.citationRodriguez-Vaamonde , S , Torresani , L , Espinosa , K & Garrote , E 2014 , Improving tag transfer for image annotation using visual and semantic information . in 2014 12th International Workshop on Content-Based Multimedia Indexing, CBMI 2014 . , 6849846 , Proceedings - International Workshop on Content-Based Multimedia Indexing , IEEE Computer Society , 12th International Workshop on Content-Based Multimedia Indexing, CBMI 2014 , Klagenfurt , Austria , 18/06/14 . https://doi.org/10.1109/CBMI.2014.6849846
dc.identifier.citationconference
dc.identifier.doi10.1109/CBMI.2014.6849846
dc.identifier.isbn9781479939909
dc.identifier.issn1949-3991
dc.identifier.urihttps://hdl.handle.net/11556/1534
dc.identifier.urlhttp://www.scopus.com/inward/record.url?scp=84904961943&partnerID=8YFLogxK
dc.language.isoeng
dc.publisherIEEE Computer Society
dc.relation.ispartof2014 12th International Workshop on Content-Based Multimedia Indexing, CBMI 2014
dc.relation.ispartofseriesProceedings - International Workshop on Content-Based Multimedia Indexing
dc.rightsinfo:eu-repo/semantics/restrictedAccess
dc.subject.keywordsImage annotation
dc.subject.keywordsImage indexing
dc.subject.keywordsmulti-modal information fusion
dc.subject.keywordstag transfer
dc.subject.keywordsComputer Graphics and Computer-Aided Design
dc.subject.keywordsInformation Systems
dc.titleImproving tag transfer for image annotation using visual and semantic informationen
dc.typeconference output
Files